© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38178
    Prev
    Next
    INDEX
    Explanations

    Ireland

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĵå±ŀ
    -0.12
    qus
    -0.10
    ToolStrip
    -0.10
    åıĺå¾Ĺ
    -0.10
    ÑģÑĤи
    -0.09
    å¤©åºľ
    -0.09
     ÑĢеÑĪа
    -0.09
    EDIA
    -0.09
     Ñĩа
    -0.09
     jspb
    -0.09
    POSITIVE LOGITS
    çĪ±å°Ķåħ°
    0.14
     Irish
    0.13
     Ireland
    0.12
    éĥ§
    0.12
    éĥ¢
    0.11
     Dublin
    0.10
    æ¹ĸåĮĹ
    0.10
    å®ľæĺĮ
    0.10
    åįģåł°
    0.10
    èķ²
    0.10
    Activations Density 0.281%

    No Known Activations